Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3955 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8425. Min Act: -0.0000

Data Index: 858831 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1332920 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8525. Min Act: -0.0000

Data Index: 804250 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8908. Min Act: -0.0000

Data Index: 496438 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8126. Min Act: -0.0000

Data Index: 284957 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8233. Min Act: -0.0000

Data Index: 143202 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8191. Min Act: -0.0000

Data Index: 746065 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8203. Min Act: -0.0000

Data Index: 1213494 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7900. Min Act: -0.0000

Data Index: 572974 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7712. Min Act: -0.0000

Data Index: 998485 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7863. Min Act: -0.0000

Data Index: 287572 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1362337 (Python Code)

Max Activating Token Index: 239

Text #12

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7663. Min Act: -0.0000

Data Index: 1601221 (Python Code)

Max Activating Token Index: 157

Text #13

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7552. Min Act: -0.0000

Data Index: 525662 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7591. Min Act: -0.0000

Data Index: 231670 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1477311 (Python Code)

Max Activating Token Index: 213

Text #16

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7693. Min Act: -0.0000

Data Index: 1226351 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7448. Min Act: -0.0000

Data Index: 797415 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7324. Min Act: -0.0000

Data Index: 1398989 (Python Code)

Max Activating Token Index: 909

Text #19

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1526004 (Python Code)

Max Activating Token Index: 36